Methods for Multi-Point Descriptors for Image Registrations

• US 20070286526A1
• Filed: 03/20/2007
• Published: 12/13/2007
• Est. Priority Date: 03/20/2006
• Status: Active Grant

• Current Assignee: General Dynamics C4 Systems Incorporated (General Dynamics Corporation), Arizona Board of Regents (University of Arizona)
• Original Assignee: University (290275) (Independent Bank Group Incorporated), Arizona Board of Regents (University of Arizona)
• Inventors: Si, Jennie, Lin, Huibao, Abousleman, Glen
• Granted Patent: US 8,417,060 B2
• Time in Patent Office: Days
• US Class Current: 382/284
• CPC Class Codes: G06T 3/4038 Image mosaicing, e.g. composing plane images from plane sub-images
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06V 10/16 using multiple overlapping images; Image stitching
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 2201/133 Survey article

Abstract

Methods for generating an image mosaic are provided. In one respect, pixels saliency of a first image and a second image are determined. One salient pixel may be selected from the determined pixels saliency group of the first image and one salient pixel may be selected from the determined pixels saliency group of the second image. A mosaicking technique of the first and second image may be performed if the one salient pixel of the first image and the one salient pixel of the second image are registered successfully.

Claims

1. A method comprising:

providing at least a first image and a second image;

selecting a similar target in the first image and the second image;

selecting at least one salient pixel from the first image and one salient pixel from the second image related to the selected target;

registering the at least one salient pixel from the first image and one salient pixel from the second image;

generating an image mosaic of the first image and second image if the registering of the at least one salient pixel is successful.

2. The method of claim 1, where the first and second images are static images or dynamic images.

3. The method of claim 1, where the first pixel and second pixel correspond to a corner pixel of the first image and second image respectively.

4. The method of claim 1, further comprising determining a saliency of a position of a pixel relative to the selected target.

5. The method of claim 4, further comprising determining a local registration of the pixel relative to the target.

6. The method of claim 1, where generating the image mosaic comprises correcting luminance variance between the first image and the second image.

7. A computer program, comprising computer or machine readable program elements translatable for implementing the method of claim 1.

8. A method comprising:

determining pixels saliency of an image;

selecting a pixel from the determined saliency pixels;

detecting surrounding images of the selected pixel;

determining a type of pixel of the selected pixel from the surrounding images; and

using the selected pixel for generating an image mosaic of two or more images.

9. The method of claim 8, where detecting surrounding images comprises determining a window around the selected pixel.

10. The method of claim 8, where using the selected pixel for generating an image mosaic comprises

registering the selected pixel;

and

generating an image mosaic if the registering of the selected pixel is successful.

11. The method of claim 8, where determining a type of pixel comprises determining a corner pixel.

12. The method of claim 8, further comprising where generating the image mosaic comprises correcting luminance variance between the first image and the second image.

13. A computer program, comprising computer or machine readable program elements translatable for implementing the method of claim 8.

14. A method for image mosaicking comprising:

determining pixels saliency of a first image;

determining pixels saliency of a second image, the second image being similar to the first image;

selecting one salient pixel from the determined pixels saliency of the first image;

selecting one salient pixel from the determined pixels saliency of the second image; and

mosaicking the first and second image if the selected salient pixels from the first and second images are successfully registered.

15. The method of claim 14, where selecting one salient pixel of the first image comprises selecting an interior pixel, an edge pixel, or a corner pixel.

16. The method of claim 14, where selecting one salient pixel of the second image comprises selecting an interior pixel, an edge pixel, or a corner pixel.

17. The method of claim 14, where the first image and the second image are static images or dynamic images.

18. The method of claim 14, further comprising correcting luminance variance between the first image and the second image.

19. A computer program, comprising computer or machine readable program elements translatable for implementing the method of claim 14.